method · first seen 14 Nov 2026
implicit function theorem
Calculus result used to compute how a solution changes with parameters, here the optimal policy with respect to design.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Gradient-Based Co-Design of Systems and Reinforcement Learning Policies with Differentiable SimulatorsPapers · 14 Nov 2026 · Akhil S. Anand, Xun Shen, Marc Peter Deisenroth, Sebastien Gros
Latest sources
- Gradient-Based Co-Design of Systems and Reinforcement Learning Policies with Differentiable SimulatorsPapers · 14 Nov 2026 · Akhil S. Anand, Xun Shen, Marc Peter Deisenroth, Sebastien Gros